Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure elements in programming files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    whitespace and indentation patterns in code and technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     faſt
    -0.53
    <unused43>
    -0.52
    <unused23>
    -0.51
    <unused41>
    -0.51
    <unused17>
    -0.51
    <unused47>
    -0.51
    <unused74>
    -0.51
    <unused42>
    -0.51
    <pad>
    -0.50
    <unused7>
    -0.50
    POSITIVE LOGITS
     diamond
    0.46
    Personendaten
    0.40
    IDTH
    0.40
    tanleria
    0.38
    color
    0.37
     Cary
    0.35
    ocere
    0.35
    monia
    0.35
     Carden
    0.35
    cen
    0.35
    Act Density 0.045%

    No Known Activations